INDEX

Explanations

a mix of words and phrases from code snippets, technical documentation, and German text related to grammar and sentence structure.

oai_token-act-pair · gemini-2.0-flash

foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

einer

-0.64

 einer

-0.56

 Potts

-0.53

 kobiety

-0.52

 osoby

-0.51

 spotkania

-0.51

 badania

-0.50

einem

-0.50

 ženy

-0.49

ně

-0.49

POSITIVE LOGITS

den

0.75

脚注の使い方

0.64

saraba

0.63

 Pristupljeno

0.61

oredCriteria

0.60

 cherchés

0.60

NameInMap

0.58

bewerken

0.57

 diesen

0.56

 okuyayım

0.56

Activations Density 0.718%

a mix of words and phrases from code snippets, technical documentation, and German text related to grammar and sentence structure.

foreign languages

No Comments

No Known Activations